© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148639
    Prev
    Next
    INDEX
    Explanations

    namesake Mim

    np_acts-logits-general · gemini-2.5-flash-lite

    personal attributes or changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thirteenth
    0.49
    툼
    0.49
     rayos
    0.46
    ṟ
    0.45
    yue
    0.44
     comien
    0.44
     eleventh
    0.44
    rs
    0.44
     astronomy
    0.44
     ৫৭
    0.43
    POSITIVE LOGITS
     Rotate
    0.50
    ნიშვნელ
    0.49
     Tutorials
    0.47
    那個
    0.47
    자가
    0.46
     variabel
    0.46
    Deviation
    0.45
     Casual
    0.45
    扦
    0.45
    Wow
    0.44
    Activations Density 0.000%

    No Known Activations